Method for generating bio-signal analysis model by utilizing bio-signal measurement frequency

Abstract

A method by which a computing device generates a bio-signal analysis model, according to one embodiment of the present disclosure, is disclosed. The method may comprise the steps of: obtaining measurement frequency data associated with bio-signal data; utilizing the bio-signal data and the measurement frequency data so as to generate a basic model for predicting a bio-signal measurement frequency; and utilizing the basic model so as to generate a bio-signal analysis model.

Description

A method for creating a biosignal analysis model by utilizing the frequency of biosignal measurements.

[0001] The present invention relates to a method for generating a biosignal analysis model, and more particularly, to a technique for generating a biosignal analysis model by utilizing measurement frequency data associated with biosignal data.

[0002] There are research results showing that it is possible to diagnose various diseases, such as abnormal blood potassium concentrations, as well as cardiovascular diseases such as coronary artery disease and arrhythmia, using electrocardiogram (ECG) signals based on deep learning technology.

[0003] The development of these disease diagnosis models is typically conducted using a supervised learning method. In this case, labels that are mapped to the ECG signals must be generated using not only the ECG signal but also medical information data (EMR) measured at a similar time to the ECG signal.

[0004] However, generating labels that are mapped to electrocardiogram signals poses a challenge for developing diagnostic models. This is because acquiring medical information data (EMR) itself is difficult, and the number of learnable electrocardiogram signals remaining after the labeling task (i.e., the task of mapping labels representing disease information) is further reduced.

[0005] Therefore, there is a need to develop a technology that can ensure the performance of disease prediction models even without performing large-scale label mapping tasks on biometric data such as electrocardiogram signals.

[0006] Korean Patent Publication No. 10-2023-0099195 (July 4, 2023) discloses a device and method for predicting the onset of heart disease based on a deep learning model using electrocardiogram data and body information.

[0007] The present disclosure aims to provide a method for effectively generating a biosignal analysis model based on measurement frequency data associated with biosignal data without a separate labeling task for the biosignal data.

[0008] Meanwhile, the technical task to be achieved by the present disclosure is not limited to the technical task mentioned above, and may include various technical tasks within a scope obvious to a person skilled in the art from the contents described below.

[0009] According to one embodiment of the present disclosure for achieving the aforementioned task, a method for generating a biosignal analysis model, which is performed by a computing device, is disclosed. The method may include: acquiring measurement frequency data associated with biosignal data; utilizing the biosignal data and the measurement frequency data to generate a basic model for predicting the measurement frequency of the biosignal; and utilizing the basic model to generate the biosignal analysis model.

[0010] In one embodiment, the step of obtaining measurement frequency data associated with the bio-signal data may include the step of obtaining measurement count information during a predetermined period before and after the time point of measurement of the bio-signal data.

[0011] In one embodiment, the biosignal analysis model is a measurement alarm model that generates alarm information that induces measurement of a biosignal, and the measurement alarm model may include the basic model; and a postprocessing module that generates the alarm information based on prediction information of the basic model.

[0012] In one embodiment, the generation frequency of the alarm information is generated based on measurement frequency information predicted by the basic model, and the alarm information may include descriptive information about the generation frequency of the alarm information.

[0013] In one embodiment, the biosignal analysis model is a disease prediction model that predicts a disease, and the step of generating the biosignal analysis model may include a step of generating the disease prediction model by tuning the basic model.

[0014] In one embodiment, the step of generating the basic model may include a step of generating the basic model by performing self-supervised learning based on a basic task of predicting a measurement frequency of a biosignal.

[0015] In one embodiment, the biosignal data includes unlabeled biosignal measurement data, and the step of tuning the basic model to generate the disease prediction model includes the step of tuning the basic model based on additional biosignal data to generate the disease prediction model, wherein the additional biosignal data may include additional biosignal measurement data and labeling data related to disease information.

[0016] In one embodiment, the biosignal data includes biosignal measurement data and labeling data related to disease information, and the step of generating the basic model includes a step of generating the basic model by utilizing the biosignal measurement data and the measurement frequency data without utilizing the labeling data, and the step of adjusting the basic model to generate the disease prediction model may include a step of adjusting the basic model based on the biosignal measurement data and the labeling data to generate the disease prediction model.

[0017] According to one embodiment of the present disclosure for achieving the above-described task, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, the computer program causes at least one processor to perform operations for generating a biosignal analysis model, the operations including: obtaining measurement frequency data associated with biosignal data; generating a basic model for predicting a measurement frequency of a biosignal by utilizing the biosignal data and the measurement frequency data; and generating the biosignal analysis model by utilizing the basic model.

[0018] A computing device according to one embodiment of the present disclosure for achieving the aforementioned task is disclosed. The device includes at least one processor; and a memory, wherein the at least one processor is configured to: acquire measurement frequency data associated with biosignal data; utilize the biosignal data and the measurement frequency data to generate a basic model for predicting the measurement frequency of the biosignal; and utilize the basic model to generate a biosignal analysis model.

[0019] According to one embodiment of the present disclosure for achieving the aforementioned task, a method for generating biosignal analysis information performed by a computing device is disclosed. The method comprises the steps of: acquiring a biosignal; and inputting the acquired biosignal into a biosignal analysis model to generate the biosignal analysis information. The biosignal analysis model may be a model generated by utilizing a basic model trained to predict the measurement frequency of learning biosignal data.

[0020] In one embodiment, the basic model may be a model learned based on a first task of predicting a measurement frequency of the learning biosignal data, and the biosignal analysis model may be a model generated by adjusting the basic model based on a second task of predicting a disease.

[0021] According to one embodiment of the present disclosure for achieving the above-described task, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, it causes at least one processor to perform operations for analyzing a biosignal, the operations including: acquiring a biosignal; and inputting the acquired biosignal into a biosignal analysis model to generate biosignal analysis information, wherein the biosignal analysis model may be a model generated by utilizing a basic model learned to predict the measurement frequency of learning biosignal data.

[0022] A user device according to one embodiment of the present disclosure for achieving the aforementioned task is disclosed. The user device includes at least one processor; and a memory, wherein the at least one processor is configured to acquire biosignal analysis information generated by a biosignal analysis model; and generate output information for transmitting the biosignal analysis information to a user, wherein the biosignal analysis model may be a model generated by utilizing a basic model learned to predict the measurement frequency of biosignal data for learning.

[0023] In one embodiment, the biosignal analysis information may include at least one of measurement notification information regarding a measurement cycle of the biosignal; or disease prediction information related to the biosignal.

[0024] In one embodiment, the biosignal analysis information may include measurement notification information regarding a measurement cycle of the biosignal, and the output information may include measurement notification information regarding a measurement cycle of the biosignal; and explanatory information regarding a basis for determining the measurement cycle.

[0025] The present disclosure can effectively generate a biosignal analysis model based on measurement frequency data associated with biosignal data, without the need for extensive labeling of the biosignal data. For example, the present disclosure generates a basic model by performing self-supervised learning based on a basic task of predicting the measurement frequency of a biosignal, and then performs fine tuning on the generated basic model based on a small amount of labeled learning data (e.g., learning data labeled with disease information), thereby effectively generating a disease prediction model without the need for extensive labeling. Furthermore, the present disclosure can effectively generate a measurement alarm model that induces the measurement of a biosignal by utilizing the basic model, without the need for additional labeled learning data.

[0026] Meanwhile, the effects of the present disclosure are not limited to the effects mentioned above, and various effects may be included within a range apparent to those skilled in the art from the contents described below.

[0027] FIG. 1 is a block diagram of a computing device for generating a biosignal analysis model according to one embodiment of the present disclosure.

[0028] FIG. 2 is a conceptual diagram illustrating a neural network according to one embodiment of the present disclosure.

[0029] FIG. 3 is a flowchart illustrating a method for creating a measurement alarm model by utilizing a basic model according to one embodiment of the present disclosure.

[0030] FIG. 4 is a flowchart illustrating a method for generating a disease prediction model by utilizing a basic model according to one embodiment of the present disclosure.

[0031] FIG. 5 is a flowchart illustrating a method for generating a biosignal analysis model according to one embodiment of the present disclosure.

[0032] FIG. 6 is a flowchart illustrating a method for generating biosignal analysis information according to one embodiment of the present disclosure.

[0033] FIG. 7 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0034] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate understanding of the present disclosure. However, it will be apparent that these embodiments may be practiced without these specific details.

[0035] As used herein, the terms "component," "module," "system," and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and / or a thread of execution. A component may be localized within a single computer. A component may be distributed between two or more computers. Furthermore, these components may execute from various computer-readable media having various data structures stored therein. Components may communicate via local and / or remote processes, for example, by signals comprising one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and / or data transmitted via signals to another system over a network such as the Internet).

[0036] Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, "X employs A or B" can apply to any of these cases. Furthermore, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated items listed.

[0037] Additionally, the terms "comprises" and / or "comprising" should be understood to imply the presence of the features and / or components in question. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, components, and / or groups thereof. Furthermore, unless otherwise specified or clear from the context to refer to the singular form, the singular in the specification and claims should generally be construed to mean "one or more."

[0038] And, the term "at least one of A or B" should be interpreted to mean "if it includes only A", "if it includes only B", or "if it is combined in the composition of A and B".

[0039] Those skilled in the art should further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0040] The description of the disclosed embodiments is provided to enable a person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present invention is not limited to the embodiments disclosed herein. The present invention is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

[0041] In the present disclosure, network function and artificial neural network and neural network can be used interchangeably.

[0042]

[0043] FIG. 1 is a block diagram of a computing device for generating a biosignal analysis model according to one embodiment of the present disclosure.

[0044] The configuration of the computing device (100) illustrated in FIG. 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing the computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

[0045] A computing device (100) may include a processor (110), memory (130), and network unit (150).

[0046] The processor (110) may be configured with one or more cores, and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in the memory (130) to perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating weights of a neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process learning of a network function. For example, a CPU and a GPGPU can jointly process network function learning and data classification using network functions. Furthermore, in one embodiment of the present disclosure, processors of multiple computing devices can be jointly used to process network function learning and data classification using network functions. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0047] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (150).

[0048] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may also operate in relation to web storage that performs the storage function of the memory (130) on the internet. The description of the above-described memory is merely an example, and the present disclosure is not limited thereto.

[0049] The network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0050] In addition, the network unit (150) presented in this specification can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA) and other systems.

[0051] In the present disclosure, the network unit (150) may be configured regardless of the communication mode, such as wired or wireless, and may be configured as various communication networks, such as a local area network (LAN), a personal area network (PAN), and a wide area network (WAN). In addition, the network may be the well-known World Wide Web (WWW), and may also utilize a wireless transmission technology used for short-distance communication, such as infrared (IrDA: Infrared Data Association) or Bluetooth.

[0052] The techniques described in this specification can be used in other networks as well as the networks mentioned above.

[0053]

[0054] FIG. 2 is a conceptual diagram illustrating a neural network according to one embodiment of the present disclosure.

[0055] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. A neural network may be comprised of a set of interconnected computational units, generally referred to as nodes. These nodes may also be referred to as neurons. A neural network comprises at least one node. The nodes (or neurons) comprising a neural network may be interconnected by one or more links.

[0056] Within a neural network, one or more nodes connected via links can form a relationship between input nodes and output nodes. The concept of input nodes and output nodes is relative, meaning that any node that is in an output node relationship with one node can also be in an input node relationship with another node, and vice versa. As described above, the relationship between input nodes and output nodes can be created based on links. One input node can be connected to one or more output nodes via links, and vice versa.

[0057] In a relationship between input nodes and output nodes connected through a single link, the data of the output node can have its value determined based on the data input to the input node. Here, the link interconnecting the input nodes and output nodes can have a weight. The weight can be variable and can be varied by the user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node through each link, the output node can determine the output node value based on the values ​​input to the input nodes connected to the output node and the weight set on the link corresponding to each input node.

[0058] As described above, a neural network is a network in which one or more nodes are interconnected through one or more links, forming input and output node relationships within the network. The characteristics of a neural network can be determined based on the number of nodes and links within the network, the relationships between the nodes and links, and the weights assigned to each link. For example, if two neural networks have the same number of nodes and links but different weight values ​​for the links, the two neural networks can be perceived as different from each other.

[0059] A neural network can be composed of a set of one or more nodes. A subset of the nodes comprising the neural network can form a layer. Some of the nodes comprising the neural network can form a layer based on their distances from the initial input node. For example, a set of nodes that are n distances from the initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links required to reach the node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a different way than described above. For example, a layer of nodes can be defined by its distance from the final output node.

[0060] An initial input node may refer to one or more nodes within a neural network into which data is directly input without going through links with other nodes. Alternatively, within a neural network, it may refer to nodes that do not have other input nodes connected by links in the relationship between nodes based on links. Similarly, a final output node may refer to one or more nodes within a neural network that do not have output nodes in their relationship with other nodes. Furthermore, a hidden node may refer to nodes that constitute a neural network other than the initial input node and the final output node.

[0061] A neural network according to one embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be the same as the number of nodes in an output layer, and the number of nodes decreases and then increases as it progresses from the input layer to the hidden layer. In addition, a neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be less than the number of nodes in an output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. In addition, a neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be greater than the number of nodes in an output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. A neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the neural networks described above.

[0062] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to input and output layers. Using DNNs, one can identify latent structures in data. For example, one can identify the latent structures of images, text, videos, audio, and music (e.g., what objects are in the image, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). DNNs can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, generative adversarial networks (GANs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Siamese networks, and generative adversarial networks (GANs). The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

[0063] In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network that outputs output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be arranged between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called a bottleneck layer (encoding), and then expanded symmetrically from the bottleneck layer to the output layer (symmetrical to the input layer). The autoencoder may perform nonlinear dimensionality reduction. The number of input layers and output layers may correspond to the dimensionality after preprocessing of the input data. In the autoencoder structure, the number of nodes in the hidden layer included in the encoder may have a structure in which the number of nodes decreases as it moves away from the input layer. The number of nodes in the bottleneck layer (the layer with the fewest nodes between the encoder and decoder) may be kept above a certain number (e.g., more than half of the input layer), as too few nodes may not transmit enough information.

[0064] Neural networks can learn through at least one of the following methods: supervised learning, self-supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning a neural network can be the process of applying knowledge to the neural network to perform a specific action.

[0065] Neural networks can be trained to minimize output errors. This process involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error. Supervised learning uses training data with the correct answer labeled for each training data (i.e., labeled training data). Unsupervised learning, on the other hand, may not have the correct answer labeled for each training data. For example, in the case of supervised learning for data classification, the training data may be data with each category labeled. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the training data labels. Alternatively, in the case of unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the neural network in the backward direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated according to the backpropagation. The amount of change in the connection weights of each node to be updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of neural network training to quickly achieve a certain level of performance, thereby increasing efficiency. A lower learning rate can be used in the later stages of training to increase accuracy.

[0066] In neural network training, training data can typically be a subset of real-world data (i.e., the data to be processed using the trained neural network). Therefore, there can be a learning cycle where errors on the training data decrease but errors on the real-world data increase. Overfitting is a phenomenon where excessive training on the training data leads to increased errors on the real-world data. For example, a neural network trained on yellow cats may fail to recognize cats when shown non-yellow colors, a type of overfitting. Overfitting can increase errors in machine learning algorithms. Various optimization methods can be used to prevent overfitting. These methods include increasing the training data, regularization, dropout, which disables some nodes in the network during the learning process, and the use of batch normalization layers.

[0067]

[0068] The present disclosure assumes that the "measurement frequency" of a biosignal has a clinical meaning (e.g., a person who measures more frequently is in a health condition requiring intensive treatment or follow-up observation), and can create a biosignal analysis model (e.g., a measurement alarm model, a disease prediction model, etc.) based on a basic task of predicting the measurement frequency of a biosignal.

[0069] For example, the computing device (100) according to one embodiment of the present disclosure may generate the biosignal analysis model based on "self-supervised learning that utilizes label-agnostic information that is not directly related to disease information (e.g., self-supervised learning that utilizes measurement frequency information)" rather than "supervised learning that requires specific labeling of disease information." In one embodiment, the computing device (100) may generate a basic model that predicts the measurement frequency of a biosignal based on a large amount of (unlabeled) biosignal data, and may generate the biosignal analysis model based on the basic model. For example, the computing device (100) may implement the measurement alarm model by post-processing the output of the basic model, and may generate the disease prediction model by fine-tuning the basic model based on additional biosignal data (in which disease-related information is labeled). In addition, the computing device (100) may generate various models by utilizing the basic model as a pretrained encoder.

[0070] Meanwhile, in the present disclosure, the measurement frequency predicted by the basic model can be understood as a result of predicting at what frequency the biosignal data input to the basic model corresponds to the measured biosignal data.

[0071] Furthermore, in the present disclosure, the labeled disease-related information may include various types of disease-related information. For example, the disease-related information may include cardiovascular disease-related information (e.g., information related to coronary artery disease, arrhythmia, etc.), nervous system disease-related information (e.g., information related to stroke, cerebral infarction, etc.), muscular disease-related information (e.g., information related to motor neuron disease, myasthenia gravis, etc.), tumor disease-related information (e.g., information related to lymphoma, cancer, etc.), etc. In addition to these examples, the disease-related information may include various types of disease-related information, such as abnormal blood potassium concentrations. In other words, the disease-related information may include various types of information related to "abnormal conditions of the body."

[0072] Meanwhile, the present disclosure can enable early detection of abnormal conditions in a patient by increasing compliance with the measurement of biosignal data (e.g., electrocardiogram signals, etc.) through personalized alarms.

[0073] Furthermore, the present disclosure utilizes the measurement alarm model to provide personalized recommended measurement frequencies (alarm information) based on biosignal data acquired from user equipment. Rather than simply providing the recommended measurement frequency (alarm information) as a push alarm, the present disclosure also provides explanatory information (information regarding the basis for the recommended measurement frequency) regarding the recommended measurement frequency, thereby ensuring that the user feels they are receiving personalized services.

[0074]

[0075] The bio-signals mentioned below may include various bio-related signals such as electrocardiogram (ECG), electromyogram (EMG), electroencephalogram (EEG), electrodermal activity (EDA), skin temperature (SKT), photoplethysmography (PPG), vital signs, X-ray image signals, magnetic resonance imaging (MRI) signals, and computed tomography (CT) image signals. In addition, the bio-signals are not limited to these examples, and may include various information obtained from a subject using a medical device, a wearable device, a mobile device, etc.

[0076]

[0077] According to one embodiment of the present disclosure, a computing device (100) may obtain measurement frequency data associated with biosignal data. In addition, the computing device (100) may utilize the biosignal data and the measurement frequency data to generate a basic model for predicting the measurement frequency of the biosignal. In addition, the computing device (100) may utilize the basic model to generate the biosignal analysis model. In one embodiment, the computing device (100) may fine-tune the basic model to generate the biosignal analysis model. For example, the computing device (100) may utilize the basic model as a pre-learning model and fine-tune the basic model based on additional biosignal data to generate the biosignal analysis model. Here, the fine-tuning of the basic model may perform various adjustment operations, such as adjustment to change (replace) the top layer of the basic model to fit a new task (e.g., alarm information generation or disease prediction), adjustment to add a new layer to the basic model, adjustment to change weights while maintaining the architecture of the basic model, etc. For example, the biosignal analysis model may be ① a measurement alarm model that generates alarm information that induces measurement of a biosignal, or ② a disease prediction model that predicts a disease, and in addition to these models, there may be various types of models related to analysis of biosignals.

[0078]

[0079] Hereinafter, an embodiment in which the biosignal analysis model is a “measurement alarm model” that generates alarm information that induces biosignal measurement will be described through FIG. 3, and an embodiment in which the biosignal analysis model is a “disease prediction model” that predicts disease will be described through FIG. 4.

[0080]

[0081] FIG. 3 is a flowchart illustrating a method for creating a measurement alarm model by utilizing a basic model according to one embodiment of the present disclosure.

[0082] According to one embodiment of the present disclosure, a computing device (100) may obtain measurement frequency data associated with biosignal data (S10). For example, the biosignal data may include unlabeled biosignal measurement data. In addition, in order to obtain the measurement frequency data, the computing device (100) may obtain measurement count information for a predetermined period before and after a measurement time of the biosignal measurement data. Here, the predetermined period may be determined as various periods including a day, a week, a month, a year, etc. In one embodiment, the computing device (100) may obtain measurement count information related to how many times a biosignal was measured during a predetermined period (e.g., 3 months) before and after a measurement time of biosignal data at a specific point in time.

[0083] In addition, the computing device (100) can determine whether the acquired measurement count information is greater than or equal to a threshold. For example, based on binary labeling, the computing device (100) can set the measurement frequency data associated with the biosignal data to 1 if the acquired measurement count information exceeds the threshold. On the other hand, the computing device (100) can set the measurement frequency data associated with the biosignal data to 0 if the acquired measurement count information is less than or equal to the threshold. However, the present invention is not limited thereto, and various embodiments may exist.

[0084]

[0085] According to one embodiment of the present disclosure, the computing device (100) can generate a basic model for predicting the measurement frequency of a biosignal by utilizing the biosignal data and the measurement frequency data (S11).

[0086] For example, the computing device (100) can generate a basic model that predicts the measurement frequency of the input biosignal data through a learning process that utilizes the biosignal data as input data and the measurement frequency data as ground truth (GT). If the measurement frequency data is set to a value of 0 or 1 based on the binary labeling discussed in step S10, the basic model can be trained as a model that generates a value between 0 and 1 corresponding to the input biosignal data. In this case, the output of the basic model can be analyzed in consideration of reference information that serves as a basis for the binary labeling. For example, if the binary labeling is performed based on "whether or not measurements were made 10 or more times during the 3 months before and after the measurement time," the output of the basic model corresponding to 0.5 can indicate that the measurement frequency of the input biosignal data is predicted to be "the frequency of being measured 5 or more times during the 3 months before and after the measurement time."

[0087]

[0088] According to one embodiment of the present disclosure, the computing device (100) can generate a measurement alarm model by utilizing the basic model (S12).

[0089] Here, the measurement alarm model can generate alarm information that induces measurement of a biosignal. In addition, the measurement alarm model can include a postprocessing module that generates the alarm information based on the basic model and prediction information of the basic model. In addition, the postprocessing module can adjust the result (measurement frequency information) generated by the basic model to generate the alarm information more accurately. In addition, the postprocessing module can generate the alarm information generation frequency and explanatory information about the alarm information generation frequency. In one embodiment, the alarm information generation frequency can be generated based on the measurement frequency information predicted by the basic model. For example, if the measurement frequency information predicted by the basic model is twice a day, the alarm information generation frequency can be generated twice a day. In addition, the alarm information can include explanatory information about the alarm information generation frequency. For example, the above explanatory information may include explanatory information such as, "As a result of analyzing the input bio-signal data with artificial intelligence, it was analyzed that the bio-signal data is analyzed with a recommended measurement frequency of twice a day, so it is necessary to perform measurements twice a day." In addition, the above explanatory information may include explanatory information such as, "Based on the measurement history of your past bio-signal data, as a result of analyzing the input bio-signal data with artificial intelligence, it was analyzed that the bio-signal data is analyzed with a recommended measurement frequency of three times a week, so it is necessary to perform measurements three times a week." Through such explanatory information, the user may be made to believe that he or she is receiving personalized services.

[0090]

[0091] FIG. 4 is a flowchart illustrating a method for generating a disease prediction model by utilizing a basic model according to one embodiment of the present disclosure.

[0092] According to one embodiment of the present disclosure, the computing device (100) may obtain measurement frequency data associated with biosignal data (S20). For example, the biosignal data may include unlabeled biosignal measurement data. In addition, the computing device (100) may obtain measurement frequency information during a predetermined period before and after a measurement time of the biosignal measurement data in order to obtain the measurement frequency data. Here, the predetermined period may be determined as various periods including a day, a week, a month, a year, etc. In one embodiment, the computing device (100) may obtain measurement frequency information related to how many times the biosignal was measured during a predetermined period (e.g., 3 months) before and after a measurement time of the biosignal data at a specific time point.

[0093] In addition, the computing device (100) can determine whether the acquired measurement count information is greater than or equal to a threshold. For example, based on binary labeling, the computing device (100) can set the measurement frequency data associated with the biosignal data to 1 if the acquired measurement count information exceeds the threshold. On the other hand, the computing device (100) can set the measurement frequency data associated with the biosignal data to 0 if the acquired measurement count information is less than or equal to the threshold. However, the present invention is not limited thereto, and various embodiments may exist.

[0094]

[0095] According to one embodiment of the present disclosure, the computing device (100) can generate a basic model for predicting the measurement frequency of a biosignal by utilizing the biosignal data and the measurement frequency data (S21).

[0096] For example, the computing device (100) can generate a basic model that predicts the measurement frequency of the input biosignal data through a learning process that utilizes the biosignal data as input data and the measurement frequency data as a correct answer (GT). If the measurement frequency data is set to a value of 0 or 1 based on the binary labeling discussed in step S20, the basic model can be trained as a model that generates a value between 0 and 1 corresponding to the input biosignal data. In this case, the output of the basic model can quantitatively represent the predicted recommended measurement frequency for the input biosignal data. For example, the closer the output of the basic model is to 0, the lower the recommended measurement frequency of the input biosignal data can be predicted, and the closer the output of the basic model is to 1, the higher the recommended measurement frequency of the input biosignal data can be predicted.

[0097] That is, the computing device (100) can generate the basic model by performing self-supervised learning based on the basic task of "predicting the measurement frequency of a biosignal." For reference, self-supervised learning is a method of training a model by automatically generating labels based on data without labels. In addition, the basic task corresponds to an auxiliary task utilized in generating such labels and may also be referred to as a pretext task.

[0098]

[0099] According to one embodiment of the present disclosure, the computing device (100) can utilize the basic model to generate a disease prediction model (S22). For reference, the disease prediction model may be a model that generates disease prediction information based on input biosignal data.

[0100] In one embodiment, the computing device (100) may generate the disease prediction model by fine-tuning the basic model based on additional bio-signal data. Here, the additional bio-signal data may be data that has been labeled with disease information, in contrast to the upper body signal data. For example, the "bio-signal data" may include "large-scale bio-signal measurement data" in which disease information is not labeled, and the "additional bio-signal data" may include "additional bio-signal measurement data" and "labeling data related to disease information." In addition, the computing device (100) may fine-tune the basic model based on a learning method that utilizes the "additional bio-signal measurement data" as input data and utilizes the "labeling data related to disease information" as correct answer data.

[0101]

[0102] According to one embodiment of the present disclosure, the computing device (100) may be user equipment. Therefore, even if the content is omitted below, the description of the computing device (100) may be equally applied to the description of the user equipment. In one embodiment, the user equipment may include at least one processor and memory. In addition, the user equipment may be a mobile device linked to a measuring device that obtains biosignal data from a subject. In addition, the user equipment may be a measuring device that obtains biosignal data from a subject. For example, the measuring device may include a portable measuring device (e.g., a smart watch, a patch, a bar-type electrocardiogram measuring device, etc.).

[0103] According to one embodiment of the present disclosure, a user device may obtain biosignal analysis information generated by a biosignal analysis model. In addition, the processor may be configured to generate output information for transmitting the biosignal analysis information to a user. Here, the biosignal analysis model may be a model generated using a "basic model learned to predict the measurement frequency of biosignal data for learning." For example, the biosignal analysis information may include at least one of measurement notification information regarding a measurement cycle of the biosignal or disease prediction information related to the biosignal. In addition, the biosignal analysis information may include measurement notification information regarding the measurement cycle of the biosignal, and the output information may include measurement notification information regarding the measurement cycle of the biosignal and explanatory information regarding a basis for determining the measurement cycle.

[0104] Meanwhile, by providing the above output information through the user equipment, the user can measure bio-signals based on personalized alarm information, enabling early detection of abnormal conditions in the user's health.

[0105]

[0106] Hereinafter, with reference to Table 1, we examine whether the “basic model for predicting the measurement frequency of biosignals” according to one embodiment of the present disclosure can perform meaningful classification operations.

[0107] Table 1 below shows the results of testing the performance of the basic model generated through a learning method that obtains "biosignal measurement data" without labeling, obtains "measurement frequency data" corresponding to the "biosignal measurement data" based on "whether measurements were performed more than 10 times during the 3 months before and after the measurement time," utilizes the biosignal measurement data as input data, and utilizes the measurement frequency data as correct answer data. For reference, the composition of the learning data set consisted of 90% training data, 5% validation data, and 5% test data.

[0108] Threshold rulemax_youdenmax_f1scoresens==specsens_90_max_specAUROC0.8951Sensitivity0.84050.63770.83240.9149Specificity0.81090.92010.8192 0.6932F1-score0.43850.51440.44540.3554PPV0.29660.43110.30400.22 05NPV0.98170.96400.98100.9885Youden0.65140.55790.65160.6081True Positive10,5197,98110,41811,450False Negative1,9964,5342,0971,065Num. Positive12,515True Negative106,959121,372108,05691,432False Positive24,94710,53423,85040,474Num. Negative131,906

[0109] As shown in Table 1, the basic model demonstrated meaningful classification capabilities for biosignals. Specifically, the basic model distinguished between biosignal data of users who frequently measured biosignals and those of users who did not, with high performance. Therefore, when utilizing this basic model as a pre-training model for "various tasks related to biosignal analysis," a target model with relatively high performance can be implemented, even in situations where training data for the target task is insufficient.

[0110] Below, based on the details described above, we will briefly review the operational flow of the present disclosure.

[0111] FIG. 5 is a flowchart illustrating a method for generating a biosignal analysis model according to one embodiment of the present disclosure.

[0112] The method for generating a biosignal analysis model illustrated in FIG. 5 can be performed by the computing device (100) described above. Therefore, even if omitted below, the description of the computing device (100) can be equally applied to the description of the method for generating a biosignal analysis model.

[0113] Referring to FIG. 5, the method for generating the biosignal analysis model may include a step of obtaining measurement frequency data associated with biosignal data (S110), a step of generating a basic model for predicting the measurement frequency of the biosignal by utilizing the biosignal data and the measurement frequency data (S120), a step of generating the biosignal analysis model by utilizing the basic model (S130), etc.

[0114] Step S110 is a step for acquiring measurement frequency data associated with biosignal data. Step S110 may include a step for acquiring measurement frequency information during a predetermined period before and after the measurement time of the biosignal data.

[0115] Step S120 is a step of generating a basic model for predicting the measurement frequency of a biosignal by utilizing the biosignal data and the measurement frequency data. Step S120 may include a step of generating the basic model by performing self-supervised learning based on the basic task of predicting the measurement frequency of a biosignal.

[0116] Step S130 is a step of generating the biosignal analysis model by utilizing the basic model. According to one embodiment, the biosignal analysis model may be ① a measurement alarm model that generates alarm information that induces measurement of a biosignal. For example, the measurement alarm model may include the basic model and a postprocessing module that generates the alarm information based on prediction information of the basic model. Alternatively, the biosignal analysis model may be ② a disease prediction model that predicts a disease. For example, step S130 may generate the disease prediction model by tuning the basic model.

[0117] In the above description, steps S110 to S130 may be further divided into additional steps or combined into fewer steps, depending on the implementation example of the present invention. Furthermore, some steps may be omitted as needed, and the order of steps may be changed.

[0118]

[0119] FIG. 6 is a flowchart illustrating a method for generating biosignal analysis information according to one embodiment of the present disclosure.

[0120] The method for generating biosignal analysis information illustrated in FIG. 6 can be performed by the computing device (100) described above. Therefore, even if omitted below, the description of the computing device (100) can be equally applied to the description of the method for generating biosignal analysis information.

[0121] Referring to FIG. 6, the method for generating the biosignal analysis information may include a step of acquiring a biosignal (S210), a step of inputting the acquired biosignal into a biosignal analysis model to generate the biosignal analysis information (S220), etc.

[0122] The above step S210 is a step of acquiring a bio-signal. Here, the bio-signal may include various bio-related signals such as electrocardiogram (ECG), electromyogram (EMG), electroencephalogram (EEG), electrodermal activity (EDA), skin temperature (SKT), photoplethysmography (PPG), vital signs, X-ray image signals, magnetic resonance imaging (MRI) signals, and computed tomography (CT) image signals. In addition, the bio-signal is not limited to these examples, and may include various information acquired from a subject using a medical device, a wearable device, a mobile device, etc.

[0123] The above step S220 is a step of generating the biosignal analysis information by inputting the acquired biosignal into a biosignal analysis model. Here, the biosignal analysis model may be a model generated by utilizing a basic model learned to predict the measurement frequency of the learning biosignal data. For example, the basic model may be a model learned based on a first task of predicting the measurement frequency of the learning biosignal data. For example, the basic model may be a model generated by performing self-supervised learning based on a first task of predicting the measurement frequency of the biosignal. In addition, the biosignal analysis model may be a model generated by adjusting the basic model based on a second task of predicting a disease. In addition, the biosignal analysis model may be a measurement alarm model that generates measurement alarm information by utilizing the output of the basic model.

[0124] In the above description, steps S210 to S220 may be further divided into additional steps or combined into fewer steps, depending on the implementation example of the present invention. Furthermore, some steps may be omitted as needed, and the order of the steps may be changed.

[0125]

[0126] Meanwhile, according to an additional embodiment of the present disclosure, “a first learning process based on a first task of predicting a measurement frequency of a biosignal (i.e., a learning process of generating the basic model)” and “a second learning process based on a second task of predicting a disease (i.e., a process of generating the disease prediction model based on the basic model)” may be performed based on “a single set of learning data”.

[0127] Specifically, ① in the preceding embodiments, the first task was implemented in the form of a pre-task performed based on "biosignal measurement data without disease information labeling", and the second task was implemented in the form of a downstream task performed based on "additional biosignal measurement data (different from the biosignal measurement data) with disease information labeling", but ② in the embodiments to be discussed below, the first task and the second task can be performed based on a single set of learning data (the same set of learning data). In other words, in the embodiments to be discussed below, a kind of multitask can be performed based on a single set of learning data to generate the basic model and the disease prediction model. According to this additional embodiment, since a model can be trained by performing a plurality of meaningful tasks in a multifaceted manner by utilizing a single set of learning data, the performance of the model can be improved and overfitting can be prevented even without additional learning data.

[0128]

[0129] A computing device (100) according to an additional embodiment of the present disclosure may acquire biosignal data (a single set of learning data) including “biosignal measurement data” and “labeling data related to disease information,” and may not acquire additional biosignal data.

[0130] In addition, the computing device (100) can perform both the generation of the basic model and the generation of the disease prediction based on the bio-signal data. For example, the computing device (100) can process the bio-signal data in a plurality of different ways (e.g., a way of ignoring labeling data and instead considering measurement frequency, a way of considering labeling data) to perform a plurality of different tasks (e.g., a task of predicting measurement frequency, a task of predicting disease), thereby generating both the basic model and the disease prediction model.

[0131] In this example, the step of generating the basic model discussed above may include a step of generating the basic model by utilizing the biosignal measurement data and measurement frequency data (obtained based on the biosignal measurement data) without utilizing the labeling data.

[0132] In addition, the step of generating the disease prediction model by adjusting the basic model may include the step of generating the disease prediction model by adjusting the basic model based on the biosignal measurement data and the labeling data.

[0133]

[0134] Meanwhile, in one embodiment, the bio-signal data (a single set of learning data) may simultaneously include ① a first type of bio-signal measurement data to which “labeling data related to disease information” is not mapped, and ② a second type of bio-signal measurement data to which “labeling data related to disease information” is mapped.

[0135] In this case, the step of generating the basic model may include a step of generating the basic model by utilizing “the first type of bio-signal measurement data,” “measurement frequency data for the first type of bio-signal measurement data,” “the second type of bio-signal measurement data,” and “measurement frequency data for the second type of bio-signal measurement data,” without utilizing labeling data mapped to the second type of bio-signal measurement data.

[0136] In addition, the step of generating the disease prediction model by adjusting the basic model may include the step of generating the disease prediction model by adjusting the basic model based on “the second type of biosignal measurement data” and “labeling data mapped to the second type of biosignal measurement.”

[0137] As a specific example, when the bio-signal corresponds to an ECG signal, the computing device (100) can divide the acquired ECG signal measurement data into “ECG signal measurement data without a label” and “ECG signal measurement data with a label,” and then ① generate the basic model by utilizing all of the acquired ECG signal measurement data without considering the label, and ② adjust the basic model by utilizing the “ECG signal measurement data with a label” to generate the disease prediction model.

[0138]

[0139] According to one embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed.

[0140] A data structure can refer to the organization, management, and storage of data to enable efficient access and modification. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval, data storage, or data modification in the shortest possible time). A data structure can also be defined as the physical or logical relationships between data elements designed to support specific data processing functions. Logical relationships between data elements can include connections between user-defined data elements. Physical relationships between data elements can include actual relationships between data elements physically stored on a computer-readable storage medium (e.g., persistent storage). Specifically, a data structure can include a collection of data, relationships between data, and functions or commands applicable to the data. An effectively designed data structure allows a computing device to perform operations while minimizing the use of its resources. Specifically, a computing device can improve the efficiency of operations, reading, inserting, deleting, comparing, exchanging, and searching through an effectively designed data structure.

[0141] Data structures can be categorized as linear or nonlinear, depending on their form. A linear data structure can be a structure in which only one data item is linked to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a series of data sets with an internal order. Lists can also include linked lists. A linked list is a data structure in which data is linked in a single line, each item having a pointer. In a linked list, a pointer can contain information about the next or previous item. Linked lists can be expressed as singly linked lists, doubly linked lists, or circular linked lists, depending on their form. A stack can be a data listing structure with limited data access. A stack can be a linear data structure in which data operations (e.g., insertion or deletion) can only be performed at one end of the data structure. Data stored in a stack can be a Last-in-First-out (LIFO) data structure. A queue is a data structure with limited access to data. Unlike a stack, it can be a first-in, first-out (FIFO) data structure, with later data being retrieved later. A deck can be a data structure that can process data at both ends.

[0142] A nonlinear data structure can be a structure in which multiple pieces of data are connected behind a single piece of data. Nonlinear data structures can include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structures can include tree data structures. A tree data structure can be a data structure in which there is only one path connecting two different vertices among multiple vertices included in the tree. In other words, it can be a data structure that does not form a loop in a graph data structure.

[0143] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, they are collectively referred to as neural networks. The data structure may include a neural network. And the data structure including the neural network may be stored on a computer-readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. The data structure including the neural network may include any of the components disclosed above. That is, the data structure including the neural network may be configured to include all or any combination of preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. In addition to the aforementioned configurations, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated in the computational process of the neural network, and is not limited to the aforementioned. The computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0144] The data structure may include data input to a neural network. The data structure including the data input to the neural network may be stored on a computer-readable medium. The data input to the neural network may include training data input during the neural network training process and / or input data input to the neural network after training has been completed. The data input to the neural network may include data that has undergone preprocessing and / or data that is the target of preprocessing. Preprocessing may include a data processing process for inputting data to the neural network. Accordingly, the data structure may include data that is the target of preprocessing and data generated by the preprocessing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0145] The data structure may include weights of the neural network. (In this specification, the terms "weight" and "parameter" may be used interchangeably.) The data structure including the weights of the neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weights may be variable and may be varied by a user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node may determine a data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set for links corresponding to each input node. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0146] By way of example and not limitation, the weights may include weights that vary during the neural network training process and / or weights that have completed neural network training. The weights that vary during the neural network training process may include weights at the start of the training cycle and / or weights that vary during the training cycle. The weights that have completed neural network training may include weights that have completed the training cycle. Accordingly, a data structure including the weights of a neural network may include a data structure including weights that vary during the neural network training process and / or weights that have completed neural network training. Therefore, the above-described weights and / or combinations of each weight are included in the data structure including the weights of a neural network. The above-described data structures are merely examples and the present disclosure is not limited thereto.

[0147] A data structure including neural network weights can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed and used. A computing device can serialize the data structure to transmit and receive data over a network. The serialized data structure including neural network weights can be reconstructed on the same or different computing devices through deserialization. The data structure including neural network weights is not limited to serialization. Furthermore, the data structure including neural network weights can include a data structure that increases computational efficiency while minimizing the use of computing device resources (e.g., a B-Tree, a Trie, an m-way search tree, an AVL tree, a Red-Black Tree in nonlinear data structures). The foregoing is merely an example, and the present disclosure is not limited thereto.

[0148] The data structure may include hyperparameters of a neural network. Furthermore, the data structure including the hyperparameters of the neural network may be stored on a computer-readable medium. The hyperparameters may be variables that can be varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle repetitions, weight initialization (e.g., setting a range of weight values ​​to be subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layer). The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0149]

[0150] FIG. 7 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0151] Although the present disclosure has been described above as being generally implemented by a computing device, those skilled in the art will appreciate that the present disclosure may be implemented in combination with computer-executable instructions and / or other program modules that may be executed on one or more computers and / or as a combination of hardware and software.

[0152] Generally, program modules include routines, programs, components, data structures, and the like that perform particular tasks or implement particular abstract data types. Furthermore, those skilled in the art will appreciate that the methods of the present disclosure can be implemented with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which may be operatively connected to one or more associated devices.

[0153] The described embodiments of the present disclosure can also be practiced in distributed computing environments, where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0154] Computers typically include a variety of computer-readable media. Computer-readable media can be any media that can be accessed by a computer, and includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media. By way of example, and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be accessed by a computer and used to store the desired information.

[0155] Computer-readable transmission media typically includes any information delivery media that embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, or other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

[0156] An exemplary environment (1100) implementing various aspects of the present disclosure is illustrated, including a computer (1102) comprising a processing unit (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including but not limited to the system memory (1106), to the processing unit (1104). The processing unit (1104) may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be utilized as the processing unit (1104).

[0157] The system bus (1108) may be any of several types of bus structures that may be additionally interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. The system memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). A basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, or EEPROM, and includes basic routines that help transfer information between components within the computer (1102), such as during start-up. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0158] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA) - which may also be configured for external use within a suitable chassis (not shown), a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from or writing to a CD-ROM disk (1122) or other high-capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128), respectively. The interface (1124) for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

[0159] These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of the computer (1102), the drives and media correspond to storing any data in a suitable digital format. While the description of computer-readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will appreciate that other types of media readable by a computer, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, may also be used in the exemplary operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

[0160] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or portions of the operating system, applications, modules, and / or data may also be cached in RAM (1112). It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0161] A user may enter commands and information into the computer (1102) via one or more wired / wireless input devices, such as a keyboard (1138) and a pointing device such as a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) that is connected to the system bus (1108), but may be connected by other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.

[0162] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface, such as a video adapter (1146). In addition to the monitor (1144), the computer typically includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0163] The computer (1102) may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communications. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), although for simplicity, only the memory storage device (1150) is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) (1152) and / or a larger network, such as a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may be connected to a worldwide computer network, such as the Internet.

[0164] When used in a LAN networking environment, the computer (1102) is connected to a local network (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communications to the LAN (1152), which may also include a wireless access point installed therein for communicating with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communications computing device on the WAN (1154), or have other means of establishing communications over the WAN (1154), such as via the Internet. The modem (1158), which may be internal or external and wired or wireless, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, program modules or portions thereof described for the computer (1102) may be stored in a remote memory / storage device (1150). It will be appreciated that the network connections depicted are exemplary and other means of establishing a communications link between the computers may be used.

[0165] The computer (1102) operates to communicate with any wireless device or object that is arranged and operates via wireless communication, such as a printer, a scanner, a desktop and / or portable computer, a portable data assistant (PDA), a communication satellite, any equipment or location associated with a radio-detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or may simply be an ad hoc communication between at least two devices.

[0166] Wi-Fi (Wireless Fidelity) enables connections to the Internet and other devices without wires. Wi-Fi is a wireless technology that allows devices, such as computers, to send and receive data anywhere within the coverage area of ​​a base station, both indoors and outdoors, similar to cell phones. Wi-Fi networks use wireless technologies called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, at data rates of, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual-band).

[0167] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0168] Those skilled in the art will appreciate that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, various forms of programs or design code (referred to herein, for convenience, as software), or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0169] The various embodiments presented herein can be implemented as a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Furthermore, various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0170] It should be understood that the specific order or hierarchy of steps in the presented processes is merely an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but are not intended to be limited to the specific order or hierarchy presented.

[0171] The description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments disclosed herein, but is to be construed in the broadest scope consistent with the principles and novel features disclosed herein.

[0172] As described above, the relevant contents have been described in the best form for carrying out the invention.

Claims

1. A method for generating a biosignal analysis model performed by a computing device, A step of obtaining measurement frequency data associated with biosignal data; A step of generating a basic model for predicting the measurement frequency of a biosignal by utilizing the biosignal data and the measurement frequency data; and A step of creating the biosignal analysis model by utilizing the above basic model. including, method.

2. In paragraph 1, The step of obtaining measurement frequency data associated with the above biosignal data is: A step of obtaining information on the number of measurements during a predetermined period before and after the measurement time of the bio-signal data, method.

3. In paragraph 1, The above biosignal analysis model is a measurement alarm model that generates alarm information that induces measurement of biosignals. The above measurement alarm model is, The above basic model; and A postprocessing module that generates the alarm information based on the prediction information of the above basic model. including, method.

4. In paragraph 3, The generation frequency of the above alarm information is generated based on the measurement frequency information predicted by the basic model, The above alarm information includes description information about the generation frequency of the above alarm information. method.

5. In paragraph 1, The above biosignal analysis model is a disease prediction model that predicts a disease, The step of creating the above biosignal analysis model is: A step of creating the disease prediction model by tuning the above basic model. including, method.

6. In paragraph 5, The steps for creating the above basic model are: A step of generating a basic model by performing self-supervised learning based on a basic task of predicting the measurement frequency of a biosignal, method.

7. In paragraph 5, The above biosignal data includes unlabeled biosignal measurement data, The step of generating the disease prediction model by adjusting the above basic model is: A step of tuning the basic model based on additional biosignal data to generate the disease prediction model is included. The above additional biosignal data includes additional biosignal measurement data and labeling data related to disease information. method.

8. In paragraph 5, The above biosignal data is, Includes biosignal measurement data and labeling data related to disease information, The steps for creating the above basic model are: A step of generating the basic model by utilizing the biosignal measurement data and the measurement frequency data without utilizing the labeling data, The step of generating the disease prediction model by adjusting the above basic model is: A step of generating the disease prediction model by adjusting the basic model based on the biosignal measurement data and the labeling data, method.

9. A computer program stored in a computer-readable storage medium, wherein when the computer program is executed by at least one processor, the computer program causes the at least one processor to perform operations for generating a biosignal analysis model, the operations comprising: An operation of obtaining measurement frequency data associated with biosignal data; An operation of generating a basic model for predicting the measurement frequency of a biosignal by utilizing the biosignal data and the measurement frequency data; and An operation of generating the biosignal analysis model by utilizing the above basic model. including, A computer program stored on a computer-readable storage medium.

10. As a computing device, at least one processor; and memory Including, At least one processor, Obtain measurement frequency data associated with biosignal data; By utilizing the above biosignal data and the above measurement frequency data, a basic model for predicting the measurement frequency of the biosignal is created; and By utilizing the above basic model, a biosignal analysis model is created, device.

11. A method for generating biosignal analysis information performed by a computing device, Step of acquiring biosignals; and A step of generating biosignal analysis information by inputting the acquired biosignal into a biosignal analysis model. Including, The above biosignal analysis model is, A model created by utilizing a basic model learned to predict the measurement frequency of biosignal data for learning. method.

12. In paragraph 11, The above basic model is a model learned based on the first task of predicting the measurement frequency of the learning biosignal data, The above biosignal analysis model is a model created by adjusting the basic model based on the second task of predicting a disease. method.

13. A computer program stored in a computer-readable storage medium, wherein when the computer program is executed by at least one processor, the computer program causes the at least one processor to perform operations for analyzing a biosignal, the operations comprising: The act of acquiring biosignals; and An operation of generating biosignal analysis information by inputting the acquired biosignal into a biosignal analysis model. Including, The above biosignal analysis model is, A model created by utilizing a basic model learned to predict the measurement frequency of biosignal data for learning. A computer program stored on a computer-readable storage medium.

14. As user equipment, at least one processor; and memory Including, At least one processor, Obtaining biosignal analysis information generated by a biosignal analysis model; and It is configured to generate output information for transmitting the above biosignal analysis information to the user, The above biosignal analysis model is, A model created by utilizing a basic model learned to predict the measurement frequency of biosignal data for learning. User equipment.

15. In paragraph 14, The above biosignal analysis information is, Measurement notification information regarding the measurement cycle of biosignals; or Disease prediction information related to biosignals Containing at least one of, User equipment.

16. In paragraph 15, The above biosignal analysis information includes measurement notification information regarding the measurement cycle of the biosignal, The above output information is, Measurement notification information regarding the measurement cycle of the above biosignal; and Explanatory information on the basis for determining the above measurement cycle including, User equipment.

Images